Merge branch 'main' of github.com:NousResearch/hermes-agent into feat/ink-refactor

This commit is contained in:
Brooklyn Nicholson
2026-04-16 08:23:20 -05:00
128 changed files with 8357 additions and 842 deletions

View File

@@ -902,7 +902,7 @@ class APIServerAdapter(BasePlatformAdapter):
return time.monotonic()
# Stream content chunks as they arrive from the agent
loop = asyncio.get_event_loop()
loop = asyncio.get_running_loop()
while True:
try:
delta = await loop.run_in_executor(None, lambda: stream_q.get(timeout=0.5))
@@ -1241,7 +1241,7 @@ class APIServerAdapter(BasePlatformAdapter):
await _emit_text_delta(it)
# Other types (non-string, non-tuple) are silently dropped.
loop = asyncio.get_event_loop()
loop = asyncio.get_running_loop()
while True:
try:
item = await loop.run_in_executor(None, lambda: stream_q.get(timeout=0.5))
@@ -2004,7 +2004,7 @@ class APIServerAdapter(BasePlatformAdapter):
callers (e.g. the SSE writer) to call ``agent.interrupt()`` from
another thread to stop in-progress LLM calls.
"""
loop = asyncio.get_event_loop()
loop = asyncio.get_running_loop()
def _run():
agent = self._create_agent(

View File

@@ -734,25 +734,56 @@ def merge_pending_message_event(
pending_messages: Dict[str, MessageEvent],
session_key: str,
event: MessageEvent,
*,
merge_text: bool = False,
) -> None:
"""Store or merge a pending event for a session.
Photo bursts/albums often arrive as multiple near-simultaneous PHOTO
events. Merge those into the existing queued event so the next turn sees
the whole burst, while non-photo follow-ups still replace the pending
event normally.
the whole burst.
When ``merge_text`` is enabled, rapid follow-up TEXT events are appended
instead of replacing the pending turn. This is used for Telegram bursty
follow-ups so a multi-part user thought is not silently truncated to only
the last queued fragment.
"""
existing = pending_messages.get(session_key)
if (
existing
and getattr(existing, "message_type", None) == MessageType.PHOTO
and event.message_type == MessageType.PHOTO
):
existing.media_urls.extend(event.media_urls)
existing.media_types.extend(event.media_types)
if event.text:
existing.text = BasePlatformAdapter._merge_caption(existing.text, event.text)
return
if existing:
existing_is_photo = getattr(existing, "message_type", None) == MessageType.PHOTO
incoming_is_photo = event.message_type == MessageType.PHOTO
existing_has_media = bool(existing.media_urls)
incoming_has_media = bool(event.media_urls)
if existing_is_photo and incoming_is_photo:
existing.media_urls.extend(event.media_urls)
existing.media_types.extend(event.media_types)
if event.text:
existing.text = BasePlatformAdapter._merge_caption(existing.text, event.text)
return
if existing_has_media or incoming_has_media:
if incoming_has_media:
existing.media_urls.extend(event.media_urls)
existing.media_types.extend(event.media_types)
if event.text:
if existing.text:
existing.text = BasePlatformAdapter._merge_caption(existing.text, event.text)
else:
existing.text = event.text
if existing_is_photo or incoming_is_photo:
existing.message_type = MessageType.PHOTO
return
if (
merge_text
and getattr(existing, "message_type", None) == MessageType.TEXT
and event.message_type == MessageType.TEXT
):
if event.text:
existing.text = f"{existing.text}\n{event.text}" if existing.text else event.text
return
pending_messages[session_key] = event
@@ -839,6 +870,11 @@ class BasePlatformAdapter(ABC):
# Gateway shutdown cancels these so an old gateway instance doesn't keep
# working on a task after --replace or manual restarts.
self._background_tasks: set[asyncio.Task] = set()
# One-shot callbacks to fire after the main response is delivered.
# Keyed by session_key. GatewayRunner uses this to defer
# background-review notifications ("💾 Skill created") until the
# primary reply has been sent.
self._post_delivery_callbacks: Dict[str, Callable] = {}
self._expected_cancelled_tasks: set[asyncio.Task] = set()
self._busy_session_handler: Optional[Callable[[MessageEvent, str], Awaitable[bool]]] = None
# Chats where auto-TTS on voice input is disabled (set by /voice off)
@@ -1905,6 +1941,14 @@ class BasePlatformAdapter(ABC):
except Exception:
pass # Last resort — don't let error reporting crash the handler
finally:
# Fire any one-shot post-delivery callback registered for this
# session (e.g. deferred background-review notifications).
_post_cb = getattr(self, "_post_delivery_callbacks", {}).pop(session_key, None)
if callable(_post_cb):
try:
_post_cb()
except Exception:
pass
# Stop typing indicator
typing_task.cancel()
try:

View File

@@ -366,6 +366,20 @@ class SlackAdapter(BasePlatformAdapter):
# in an assistant-enabled context. Falls back to reactions.
logger.debug("[Slack] assistant.threads.setStatus failed: %s", e)
def _dm_top_level_threads_as_sessions(self) -> bool:
"""Whether top-level Slack DMs get per-message session threads.
Defaults to ``True`` so each visible DM reply thread is isolated as its
own Hermes session — matching the per-thread behavior channels already
have. Set ``platforms.slack.extra.dm_top_level_threads_as_sessions``
to ``false`` in config.yaml to revert to the legacy behavior where all
top-level DMs share one continuous session.
"""
raw = self.config.extra.get("dm_top_level_threads_as_sessions")
if raw is None:
return True # default: each DM thread is its own session
return str(raw).strip().lower() in ("1", "true", "yes", "on")
def _resolve_thread_ts(
self,
reply_to: Optional[str] = None,
@@ -996,10 +1010,14 @@ class SlackAdapter(BasePlatformAdapter):
# Build thread_ts for session keying.
# In channels: fall back to ts so each top-level @mention starts a
# new thread/session (the bot always replies in a thread).
# In DMs: only use the real thread_ts — top-level DMs should share
# one continuous session, threaded DMs get their own session.
# In DMs: fall back to ts so each top-level DM reply thread gets
# its own session key (matching channel behavior). Set
# dm_top_level_threads_as_sessions: false in config to revert to
# legacy single-session-per-DM-channel behavior.
if is_dm:
thread_ts = event.get("thread_ts") or assistant_meta.get("thread_ts") # None for top-level DMs
thread_ts = event.get("thread_ts") or assistant_meta.get("thread_ts")
if not thread_ts and self._dm_top_level_threads_as_sessions():
thread_ts = ts
else:
thread_ts = event.get("thread_ts") or ts # ts fallback for channels

View File

@@ -18,6 +18,10 @@ logger = logging.getLogger(__name__)
try:
from telegram import Update, Bot, Message, InlineKeyboardButton, InlineKeyboardMarkup
try:
from telegram import LinkPreviewOptions
except ImportError:
LinkPreviewOptions = None
from telegram.ext import (
Application,
CommandHandler,
@@ -36,6 +40,7 @@ except ImportError:
Message = Any
InlineKeyboardButton = Any
InlineKeyboardMarkup = Any
LinkPreviewOptions = None
Application = Any
CommandHandler = Any
CallbackQueryHandler = Any
@@ -129,6 +134,7 @@ class TelegramAdapter(BasePlatformAdapter):
# When a chunk is near this limit, a continuation is almost certain.
_SPLIT_THRESHOLD = 4000
MEDIA_GROUP_WAIT_SECONDS = 0.8
_GENERAL_TOPIC_THREAD_ID = "1"
def __init__(self, config: PlatformConfig):
super().__init__(config, Platform.TELEGRAM)
@@ -137,6 +143,7 @@ class TelegramAdapter(BasePlatformAdapter):
self._webhook_mode: bool = False
self._mention_patterns = self._compile_mention_patterns()
self._reply_to_mode: str = getattr(config, 'reply_to_mode', 'first') or 'first'
self._disable_link_previews: bool = self._coerce_bool_extra("disable_link_previews", False)
# Buffer rapid/album photo updates so Telegram image bursts are handled
# as a single MessageEvent instead of self-interrupting multiple turns.
self._media_batch_delay_seconds = float(os.getenv("HERMES_TELEGRAM_MEDIA_BATCH_DELAY_SECONDS", "0.8"))
@@ -172,6 +179,29 @@ class TelegramAdapter(BasePlatformAdapter):
allowed_ids = {uid.strip() for uid in allowed_csv.split(",") if uid.strip()}
return "*" in allowed_ids or user_id in allowed_ids
@classmethod
def _metadata_thread_id(cls, metadata: Optional[Dict[str, Any]]) -> Optional[str]:
if not metadata:
return None
thread_id = metadata.get("thread_id") or metadata.get("message_thread_id")
return str(thread_id) if thread_id is not None else None
@classmethod
def _message_thread_id_for_send(cls, thread_id: Optional[str]) -> Optional[int]:
if not thread_id or str(thread_id) == cls._GENERAL_TOPIC_THREAD_ID:
return None
return int(thread_id)
@classmethod
def _message_thread_id_for_typing(cls, thread_id: Optional[str]) -> Optional[int]:
if not thread_id:
return None
return int(thread_id)
@staticmethod
def _is_thread_not_found_error(error: Exception) -> bool:
return "thread not found" in str(error).lower()
def _fallback_ips(self) -> list[str]:
"""Return validated fallback IPs from config (populated by _apply_env_overrides)."""
configured = self.config.extra.get("fallback_ips", []) if getattr(self.config, "extra", None) else []
@@ -202,6 +232,26 @@ class TelegramAdapter(BasePlatformAdapter):
pass
return isinstance(error, OSError)
def _coerce_bool_extra(self, key: str, default: bool = False) -> bool:
value = self.config.extra.get(key) if getattr(self.config, "extra", None) else None
if value is None:
return default
if isinstance(value, str):
lowered = value.strip().lower()
if lowered in ("true", "1", "yes", "on"):
return True
if lowered in ("false", "0", "no", "off"):
return False
return default
return bool(value)
def _link_preview_kwargs(self) -> Dict[str, Any]:
if not getattr(self, "_disable_link_previews", False):
return {}
if LinkPreviewOptions is not None:
return {"link_preview_options": LinkPreviewOptions(is_disabled=True)}
return {"disable_web_page_preview": True}
async def _handle_polling_network_error(self, error: Exception) -> None:
"""Reconnect polling after a transient network interruption.
@@ -549,7 +599,7 @@ class TelegramAdapter(BasePlatformAdapter):
"write_timeout": _env_float("HERMES_TELEGRAM_HTTP_WRITE_TIMEOUT", 20.0),
}
proxy_url = resolve_proxy_url()
proxy_url = resolve_proxy_url("TELEGRAM_PROXY")
disable_fallback = (os.getenv("HERMES_TELEGRAM_DISABLE_FALLBACK_IPS", "").strip().lower() in ("1", "true", "yes", "on"))
fallback_ips = self._fallback_ips()
if not fallback_ips:
@@ -615,14 +665,14 @@ class TelegramAdapter(BasePlatformAdapter):
from telegram.error import NetworkError, TimedOut
except ImportError:
NetworkError = TimedOut = OSError # type: ignore[misc,assignment]
_max_connect = 3
_max_connect = 8
for _attempt in range(_max_connect):
try:
await self._app.initialize()
break
except (NetworkError, TimedOut, OSError) as init_err:
if _attempt < _max_connect - 1:
wait = 2 ** _attempt
wait = min(2 ** _attempt, 15)
logger.warning(
"[%s] Connect attempt %d/%d failed: %s — retrying in %ds",
self.name, _attempt + 1, _max_connect, init_err, wait,
@@ -823,7 +873,7 @@ class TelegramAdapter(BasePlatformAdapter):
]
message_ids = []
thread_id = metadata.get("thread_id") if metadata else None
thread_id = self._metadata_thread_id(metadata)
try:
from telegram.error import NetworkError as _NetErr
@@ -843,7 +893,7 @@ class TelegramAdapter(BasePlatformAdapter):
for i, chunk in enumerate(chunks):
should_thread = self._should_thread_reply(reply_to, i)
reply_to_id = int(reply_to) if should_thread else None
effective_thread_id = int(thread_id) if thread_id else None
effective_thread_id = self._message_thread_id_for_send(thread_id)
msg = None
for _send_attempt in range(3):
@@ -856,6 +906,7 @@ class TelegramAdapter(BasePlatformAdapter):
parse_mode=ParseMode.MARKDOWN_V2,
reply_to_message_id=reply_to_id,
message_thread_id=effective_thread_id,
**self._link_preview_kwargs(),
)
except Exception as md_error:
# Markdown parsing failed, try plain text
@@ -868,6 +919,7 @@ class TelegramAdapter(BasePlatformAdapter):
parse_mode=None,
reply_to_message_id=reply_to_id,
message_thread_id=effective_thread_id,
**self._link_preview_kwargs(),
)
else:
raise
@@ -878,8 +930,7 @@ class TelegramAdapter(BasePlatformAdapter):
# (not transient network issues). Detect and handle
# specific cases instead of blindly retrying.
if _BadReq and isinstance(send_err, _BadReq):
err_lower = str(send_err).lower()
if "thread not found" in err_lower and effective_thread_id is not None:
if self._is_thread_not_found_error(send_err) and effective_thread_id is not None:
# Thread doesn't exist — retry without
# message_thread_id so the message still
# reaches the chat.
@@ -889,6 +940,7 @@ class TelegramAdapter(BasePlatformAdapter):
)
effective_thread_id = None
continue
err_lower = str(send_err).lower()
if "message to be replied not found" in err_lower and reply_to_id is not None:
# Original message was deleted before we
# could reply — clear reply target and retry
@@ -1055,6 +1107,7 @@ class TelegramAdapter(BasePlatformAdapter):
text=text,
parse_mode=ParseMode.MARKDOWN,
reply_markup=keyboard,
**self._link_preview_kwargs(),
)
return SendResult(success=True, message_id=str(msg.message_id))
except Exception as e:
@@ -1076,16 +1129,17 @@ class TelegramAdapter(BasePlatformAdapter):
try:
cmd_preview = command[:3800] + "..." if len(command) > 3800 else command
# Escape backticks that would break Markdown v1 inline code parsing
safe_cmd = cmd_preview.replace("`", "'")
safe_desc = description.replace("`", "'").replace("*", "")
text = (
f"⚠️ *Command Approval Required*\n\n"
f"`{cmd_preview}`\n\n"
f"Reason: {description}"
f"`{safe_cmd}`\n\n"
f"Reason: {safe_desc}"
)
# Resolve thread context for thread replies
thread_id = None
if metadata:
thread_id = metadata.get("thread_id") or metadata.get("message_thread_id")
thread_id = self._metadata_thread_id(metadata)
# We'll use the message_id as part of callback_data to look up session_key
# Send a placeholder first, then update — or use a counter.
@@ -1111,9 +1165,11 @@ class TelegramAdapter(BasePlatformAdapter):
"text": text,
"parse_mode": ParseMode.MARKDOWN,
"reply_markup": keyboard,
**self._link_preview_kwargs(),
}
if thread_id:
kwargs["message_thread_id"] = int(thread_id)
message_thread_id = self._message_thread_id_for_send(thread_id)
if message_thread_id is not None:
kwargs["message_thread_id"] = message_thread_id
msg = await self._bot.send_message(**kwargs)
@@ -1181,6 +1237,7 @@ class TelegramAdapter(BasePlatformAdapter):
parse_mode=ParseMode.MARKDOWN,
reply_markup=keyboard,
message_thread_id=int(thread_id) if thread_id else None,
**self._link_preview_kwargs(),
)
# Store picker state keyed by chat_id
@@ -1545,23 +1602,23 @@ class TelegramAdapter(BasePlatformAdapter):
with open(audio_path, "rb") as audio_file:
# .ogg files -> send as voice (round playable bubble)
if audio_path.endswith((".ogg", ".opus")):
_voice_thread = metadata.get("thread_id") if metadata else None
_voice_thread = self._metadata_thread_id(metadata)
msg = await self._bot.send_voice(
chat_id=int(chat_id),
voice=audio_file,
caption=caption[:1024] if caption else None,
reply_to_message_id=int(reply_to) if reply_to else None,
message_thread_id=int(_voice_thread) if _voice_thread else None,
message_thread_id=self._message_thread_id_for_send(_voice_thread),
)
else:
# .mp3 and others -> send as audio file
_audio_thread = metadata.get("thread_id") if metadata else None
_audio_thread = self._metadata_thread_id(metadata)
msg = await self._bot.send_audio(
chat_id=int(chat_id),
audio=audio_file,
caption=caption[:1024] if caption else None,
reply_to_message_id=int(reply_to) if reply_to else None,
message_thread_id=int(_audio_thread) if _audio_thread else None,
message_thread_id=self._message_thread_id_for_send(_audio_thread),
)
return SendResult(success=True, message_id=str(msg.message_id))
except Exception as e:
@@ -1591,14 +1648,14 @@ class TelegramAdapter(BasePlatformAdapter):
if not os.path.exists(image_path):
return SendResult(success=False, error=f"Image file not found: {image_path}")
_thread = metadata.get("thread_id") if metadata else None
_thread = self._metadata_thread_id(metadata)
with open(image_path, "rb") as image_file:
msg = await self._bot.send_photo(
chat_id=int(chat_id),
photo=image_file,
caption=caption[:1024] if caption else None,
reply_to_message_id=int(reply_to) if reply_to else None,
message_thread_id=int(_thread) if _thread else None,
message_thread_id=self._message_thread_id_for_send(_thread),
)
return SendResult(success=True, message_id=str(msg.message_id))
except Exception as e:
@@ -1629,7 +1686,7 @@ class TelegramAdapter(BasePlatformAdapter):
return SendResult(success=False, error=f"File not found: {file_path}")
display_name = file_name or os.path.basename(file_path)
_thread = metadata.get("thread_id") if metadata else None
_thread = self._metadata_thread_id(metadata)
with open(file_path, "rb") as f:
msg = await self._bot.send_document(
@@ -1638,7 +1695,7 @@ class TelegramAdapter(BasePlatformAdapter):
filename=display_name,
caption=caption[:1024] if caption else None,
reply_to_message_id=int(reply_to) if reply_to else None,
message_thread_id=int(_thread) if _thread else None,
message_thread_id=self._message_thread_id_for_send(_thread),
)
return SendResult(success=True, message_id=str(msg.message_id))
except Exception as e:
@@ -1662,14 +1719,14 @@ class TelegramAdapter(BasePlatformAdapter):
if not os.path.exists(video_path):
return SendResult(success=False, error=f"Video file not found: {video_path}")
_thread = metadata.get("thread_id") if metadata else None
_thread = self._metadata_thread_id(metadata)
with open(video_path, "rb") as f:
msg = await self._bot.send_video(
chat_id=int(chat_id),
video=f,
caption=caption[:1024] if caption else None,
reply_to_message_id=int(reply_to) if reply_to else None,
message_thread_id=int(_thread) if _thread else None,
message_thread_id=self._message_thread_id_for_send(_thread),
)
return SendResult(success=True, message_id=str(msg.message_id))
except Exception as e:
@@ -1699,13 +1756,13 @@ class TelegramAdapter(BasePlatformAdapter):
try:
# Telegram can send photos directly from URLs (up to ~5MB)
_photo_thread = metadata.get("thread_id") if metadata else None
_photo_thread = self._metadata_thread_id(metadata)
msg = await self._bot.send_photo(
chat_id=int(chat_id),
photo=image_url,
caption=caption[:1024] if caption else None, # Telegram caption limit
reply_to_message_id=int(reply_to) if reply_to else None,
message_thread_id=int(_photo_thread) if _photo_thread else None,
message_thread_id=self._message_thread_id_for_send(_photo_thread),
)
return SendResult(success=True, message_id=str(msg.message_id))
except Exception as e:
@@ -1728,6 +1785,7 @@ class TelegramAdapter(BasePlatformAdapter):
photo=image_data,
caption=caption[:1024] if caption else None,
reply_to_message_id=int(reply_to) if reply_to else None,
message_thread_id=self._message_thread_id_for_send(_photo_thread),
)
return SendResult(success=True, message_id=str(msg.message_id))
except Exception as e2:
@@ -1753,13 +1811,13 @@ class TelegramAdapter(BasePlatformAdapter):
return SendResult(success=False, error="Not connected")
try:
_anim_thread = metadata.get("thread_id") if metadata else None
_anim_thread = self._metadata_thread_id(metadata)
msg = await self._bot.send_animation(
chat_id=int(chat_id),
animation=animation_url,
caption=caption[:1024] if caption else None,
reply_to_message_id=int(reply_to) if reply_to else None,
message_thread_id=int(_anim_thread) if _anim_thread else None,
message_thread_id=self._message_thread_id_for_send(_anim_thread),
)
return SendResult(success=True, message_id=str(msg.message_id))
except Exception as e:
@@ -1776,12 +1834,23 @@ class TelegramAdapter(BasePlatformAdapter):
"""Send typing indicator."""
if self._bot:
try:
_typing_thread = metadata.get("thread_id") if metadata else None
await self._bot.send_chat_action(
chat_id=int(chat_id),
action="typing",
message_thread_id=int(_typing_thread) if _typing_thread else None,
)
_typing_thread = self._metadata_thread_id(metadata)
message_thread_id = self._message_thread_id_for_typing(_typing_thread)
try:
await self._bot.send_chat_action(
chat_id=int(chat_id),
action="typing",
message_thread_id=message_thread_id,
)
except Exception as e:
if message_thread_id is not None and self._is_thread_not_found_error(e):
await self._bot.send_chat_action(
chat_id=int(chat_id),
action="typing",
message_thread_id=None,
)
else:
raise
except Exception as e:
# Typing failures are non-fatal; log at debug level only.
logger.debug(
@@ -2726,7 +2795,9 @@ class TelegramAdapter(BasePlatformAdapter):
# Resolve DM topic name and skill binding
thread_id_raw = message.message_thread_id
thread_id_str = str(thread_id_raw) if thread_id_raw else None
thread_id_str = str(thread_id_raw) if thread_id_raw is not None else None
if chat_type == "group" and thread_id_str is None and getattr(chat, "is_forum", False):
thread_id_str = self._GENERAL_TOPIC_THREAD_ID
chat_topic = None
topic_skill = None

View File

@@ -46,7 +46,7 @@ _SEED_FALLBACK_IPS: list[str] = ["149.154.167.220"]
def _resolve_proxy_url() -> str | None:
# Delegate to shared implementation (env vars + macOS system proxy detection)
from gateway.platforms.base import resolve_proxy_url
return resolve_proxy_url()
return resolve_proxy_url("TELEGRAM_PROXY")
class TelegramFallbackTransport(httpx.AsyncBaseTransport):

View File

@@ -258,6 +258,20 @@ class WecomCallbackAdapter(BasePlatformAdapter):
)
event = self._build_event(app, decrypted)
if event is not None:
# Deduplicate: WeCom retries callbacks on timeout,
# producing duplicate inbound messages (#10305).
if event.message_id:
now = time.time()
if event.message_id in self._seen_messages:
if now - self._seen_messages[event.message_id] < MESSAGE_DEDUP_TTL_SECONDS:
logger.debug("[WecomCallback] Duplicate MsgId %s, skipping", event.message_id)
return web.Response(text="success", content_type="text/plain")
del self._seen_messages[event.message_id]
self._seen_messages[event.message_id] = now
# Prune expired entries when cache grows large
if len(self._seen_messages) > 2000:
cutoff = now - MESSAGE_DEDUP_TTL_SECONDS
self._seen_messages = {k: v for k, v in self._seen_messages.items() if v > cutoff}
# Record which app this user belongs to.
if event.source and event.source.user_id:
map_key = self._user_app_key(